CN110930372B - An image processing method, electronic device, and computer-readable storage medium - Google Patents

Abstract

An embodiment of the present invention provides an image processing method, an electronic device, and a computer-readable storage medium, wherein the image processing method includes: acquiring continuous P images in a target scene collected by a camera, where P is a positive integer; The light source category under the target scene, the light source category includes natural light source and artificial light source; if the light source category is artificial light source, perform color band detection on the P images; if detected from the P images The color band is to perform color band elimination processing on the P images; output the image after the color band is eliminated. According to the image processing method of the embodiment of the present invention, the light source type can be determined according to the acquired light source type information to determine whether the image acquired by the camera needs to be detected and eliminated, which not only simplifies the color band detection process, but also reduces false detection Possibility to improve image processing speed.

Description

An image processing method, electronic device, and computer-readable storage medium

technical field

Embodiments of the present invention relate to the technical field of image processing, and in particular, to an image processing method, electronic equipment, and a computer-readable storage medium.

Background technique

At present, the CMOS (Complementary Metal Oxide Semiconductor) of the camera used in electronic equipment is exposed line by line. Therefore, in different photographing environments, due to light sources of different frequencies, the images captured by electronic equipment There will be banding (ribbon) phenomenon, which seriously affects the image quality of electronic equipment.

For banding (ribbon) phenomena, existing solutions mainly focus on the process of banding detection and banding elimination. However, the existing solutions have disadvantages such as cumbersome color band detection process, low detection accuracy, and slow image processing speed.

Contents of the invention

Embodiments of the present invention provide an image processing method, electronic equipment, and a computer-readable storage medium to solve the problems in the prior art of cumbersome color band detection process, poor detection effect, and slow image processing speed.

In order to solve the problems of the technologies described above, the present invention is achieved in that:

In a first aspect, an embodiment of the present invention provides an image processing method, including:

Obtain consecutive P images of the target scene collected by the camera, where P is a positive integer;

identifying a light source category in the target scene, where the light source category includes natural light sources and artificial light sources;

If the light source category is an artificial light source, perform color band detection on the P images;

If a color band is detected from the P images, performing color band elimination processing on the P images;

Output the image with the color band removed.

In a second aspect, an embodiment of the present invention provides an electronic device, including:

The obtaining module is used to obtain continuous P images under the target scene collected by the camera, where P is a positive integer;

An identification module, configured to identify the category of light sources in the target scene, where the categories of light sources include natural light sources and artificial light sources;

A color band detection module, configured to perform color band detection on the P images if the light source type is an artificial light source;

A color band elimination module, configured to perform color band elimination processing on the P images if a color band is detected from the P images;

The image output module is used for outputting the image after removing the color band.

In a third aspect, an embodiment of the present invention provides an electronic device, including a processor, a memory, and a computer program stored in the memory and operable on the processor, and the computer program is executed by the processor When implementing the steps of the image processing method as described above.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned image processing method are implemented.

In the embodiment of the present invention, before performing the color band detection, the light source category is determined according to the obtained light source category information to determine whether the image acquired by the camera needs to be detected and eliminated, which not only simplifies the process of color band detection, but also reduces the The possibility of false detection is reduced, and the image processing speed is improved.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiment. The drawings are only for the purpose of illustrating a preferred embodiment and are not to be considered as limiting the invention. Also throughout the drawings, the same reference numerals are used to designate the same components. In the attached picture:

FIG. 1 is one of the schematic flow charts of an image processing method provided by an embodiment of the present invention;

Fig. 2 is a schematic diagram of the retinal cerebral cortex theory provided by the embodiment of the present invention;

3 is a schematic diagram of a target color band elimination model provided by an embodiment of the present invention;

FIG. 4 is one of the structural schematic diagrams of an electronic device provided by an embodiment of the present invention;

FIG. 5 is the second structural schematic diagram of an electronic device provided by an embodiment of the present invention;

FIG. 6 is a third structural schematic diagram of an electronic device provided by an embodiment of the present invention.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

The term "comprising" and any variations thereof in the description and claims of this application are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or device comprising a series of steps or units is not necessarily limited to the explicit instead of those steps or elements explicitly listed, other steps or elements not explicitly listed or inherent to the process, method, product or apparatus may be included. In addition, the use of "and/or" in the description and claims means at least one of the connected objects, such as A and/or B, means that there are three situations including A alone, B alone, and both A and B.

In the embodiments of the present invention, words such as "exemplary" or "for example" are used as examples, illustrations or illustrations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present invention shall not be construed as being more preferred or more advantageous than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete manner.

Please refer to FIG. 1 , which is a schematic flowchart of an image processing method provided by an embodiment of the present invention. As shown in Figure 1, the image processing method of the embodiment of the present invention includes the following steps:

(1) Step 101: Acquire consecutive P images of the target scene captured by the camera, where P is a positive integer.

Specifically, in step 101, the camera of the electronic device includes various sensors and other components. Through the camera of the electronic device, multiple continuous images of the target scene can be collected, where the continuous multiple images are at time Multiple consecutive images, one image is also one frame of image.

(2) Step 102, identifying the type of light source in the target scene, where the type of light source includes natural light source and artificial light source.

In step 102, the image captured by the camera is the target scene. In the target scene, the light source may be a natural light source, such as the sun, or an artificial light source, such as a fluorescent lamp or an incandescent lamp.

In the embodiment of the present invention, the step of identifying the light source category in the target scene in step 102 may specifically include:

Step 1021: Obtain color information by using the color sensor of the camera;

Step 1022: Determine light source information according to the color information, and the light source information includes at least one of color rendering index and correlated color temperature;

Step 1023: Determine the type of light source in the target scene according to the light source information.

More specifically, while the camera is shooting continuous images, it uses the color sensor of the camera to obtain the color information of the current target scene, and then determines the light source information according to the color information obtained by the color sensor. The light source information includes color rendering index (CRI) and at least one of correlated color temperature (CCT).

Preferably, in order to improve the accuracy of identifying the light source category, in the embodiment of the present invention, the light source estimation model can be used for identification, that is, after the light source information is obtained, the light source estimation model can be used to analyze the collected light source Information is estimated to determine whether the light source category in the target scene is a natural light source or an artificial light source. Among them, the light source estimation model can be a K-nearest neighbor model or a convolutional neural network model. By pre-constructing the model and performing light source category recognition training on it, the light source estimation model can be used to estimate the light source category. The specific learning and training process is the existing technology, which will not be repeated here. It can be known that the more sufficient the training and learning of the light source estimation model is, the higher the estimation accuracy will be. Moreover, using the color rendering index (CRI) and correlated color temperature (CCT) data information to estimate the light source type can also improve the accuracy of the estimation. Automatically obtain the color rendering index (CRI) and/or correlated color temperature (CCT) through the camera, which can realize the automatic identification of the light source category and improve the user experience.

In other embodiments of the present invention, the identification of the light source category under the target scene in step 102 may also be performed in the following manner:

The electronic device directly receives the input for determining the type of light source, that is, while the camera captures continuous images, the electronic device provides options for the type of light source. The options may include natural light source options and artificial light source options. When the electronic device receives the selection When the natural light source option is input, the light source category can be determined as natural light source, and when the electronic device receives an input for selecting the artificial light source option, it can be determined that the light source category is artificial light source. In this way, human intervention can be increased, and computing processing of electronic equipment can be saved.

(3) Step 103: If the type of light source is not a natural light source, perform color band detection on the acquired P images, and judge whether a color band is detected from the P images.

Furthermore, based on the principle of CMOS progressive exposure of the camera, it can be known that the exposure time between the lines of the image is the same, and for the light source with a frequency that does not match the exposure time of the CMOS, the brightness obtained by each line is inconsistent, and the image captured by this is inconsistent. The phenomenon of banding, the phenomenon of banding means that there are color bands in the image, and band means color bands and bands. It can be found that the two necessary conditions for banding are: the progressive exposure principle of CMOS and the artificial light source with a frequency that does not match the exposure time of CMOS. That is to say, when there is only natural light source, there will be no banding phenomenon in the captured image. Therefore, when the result of step 102 shows that the light source type is not a natural light source, there may be color bands in the image captured by the camera, so in this case, in order to improve user experience, it is necessary to detect whether the image has color bands.

According to the above analysis, if the light source type is an artificial light source, the color band detection is performed on the acquired P consecutive images. Specifically, the above step 103 may include:

Step 1031: Obtain a target detection image according to the P images;

Step 1032: Input the target detection image into the target color band detection model to detect whether there is a color band.

Wherein, the target color band detection model is used to detect whether there is a color band in the image. In some specific embodiments of the present invention, the target color band detection model can specifically be a convolutional neural network model. Since the target color band detection model requires pre-training learning , therefore, before step 1032, the following steps may also be included:

First, obtain S image samples for training. The S image samples include images with artificial light sources as light sources and images with natural light sources as light sources. Each image sample includes M consecutive images, where S and M are is a positive integer, and S=M; of course, the more image samples, the better the training effect, and the higher the detection accuracy of the target color band detection model.

Then, perform difference calculation between each frame of image in each image sample and another frame of image, that is, time difference calculation of pixels, for example, each image sample includes 6 consecutive images, which are respectively X ₁ , X ₂ , X ₃ , X ₄ , X ₅ , X ₆ , X ₂ -X ₁ , X ₄ -X ₃ , X ₆ -X ₅ can be used for differential calculation, or X ₆ -X ₄ , X ₅ -X ₃ , X ₄ -X ₂ , X ₃ -X ₁ for differential calculation, and X ₆ -X ₅ , X ₅ -X ₄ , X ₄ -X ₃ , X ₃ -X ₂ , X ₂ -X ₁ for differential calculation , as long as any two images in each image sample can be differentially calculated, but it must be ensured that each image has been differentially calculated.

Next, image fusion is performed on the multiple frame difference images obtained after difference calculation to finally obtain a target sample image. It can be determined that S image samples will eventually obtain S RGB target sample images.

In the above image fusion process, since there may be some flaws in the image fusion, optionally, after the image fusion, image preprocessing can be further performed on the fused image, such as whitening processing, resizing, deformation, etc., In this way, a target sample image with a better processing result can be obtained, which is conducive to improving the detection accuracy of the target color band detection model.

Finally, construct a convolutional neural network model, use the obtained S target sample images to train the convolutional neural network model, so that it can continuously learn to detect color bands, so as to obtain a convolutional neural network model that can be used to detect color bands, namely Object Ribbon Detection Model.

Using the trained and learned convolutional neural network model to detect color bands in images can effectively improve the accuracy and efficiency of detection.

Further, the above step 1031 may specifically include the following steps:

Select consecutive M frames of images from the acquired P images at each interval of the target duration, and the interval target duration can be set to a value such as 5s, 6s, etc., wherein P and M are positive integers, and M≤P;

Calculate the difference between each frame of the selected M frames of images and any other frame of images, that is, calculate the time difference of pixels. For example, each image sample includes 6 consecutive frames of images, which are respectively X ₁ , X ₂ , X ₃ , X ₄ , X ₅ , X ₆ , X ₂ -X ₁ , X ₄ -X ₃ , X ₆ -X ₅ can be used for differential calculation, or X ₆ -X ₄ , X ₅ -X ₃ , X ₄ -X ₂ , X ₃ -X ₁ for differential calculation, and X ₆ -X ₅ , X ₅ -X ₄ , X ₄ -X ₃ , X ₃ -X ₂ , X ₂ -X ₁ for differential calculation , as long as any two frames of images in each image sample can be differentially calculated, but it must be ensured that each frame of image has been differentially calculated; that is, a part of the images can be selected from the P images for the above differential calculation process, or use all P images to perform the above-mentioned difference calculation process;

Then, image fusion is performed on multiple frame difference images obtained after difference calculation, and finally a target detection image is obtained.

In the above image fusion process, since there may be some flaws in the image fusion, optionally, after the image fusion, image preprocessing can be further performed on the fused image, such as whitening processing, resizing, deformation, etc., In this way, a target detection image with better processing results can be obtained, which is conducive to improving the detection accuracy of the target color band detection model.

Preferably, the above-mentioned step of performing image processing on the P images to obtain the target detection image should be consistent with the above-mentioned step of obtaining the target sample image during the training of the target color band detection model, so as to improve the accuracy of the color band detection.

(4) Step 104: If color bands are detected from the P images, perform color band removal processing on the P images.

That is to say or, after step 1032, if a color band is detected in the target detection image, it is necessary to eliminate the color band on the P images captured by the camera. Specifically, step 104 may include:

Step 1041: Input the P images into the target color band elimination model, and eliminate the color bands in the P images.

In some specific embodiments of the present invention, the target color band elimination model can specifically be a convolutional neural network model. Since the target color band elimination model requires pre-training and learning, the following steps are also included before step 1041:

First, obtain image samples with color bands and image samples without color bands in the same scene. The method of acquisition can be by means of controlling the light source, that is, to obtain image samples with color bands in the scene of artificial light source, and then the scene The light source is replaced with a natural light source, so as to obtain image samples without color bands (equivalent to image samples after color band elimination); of course, the more image samples acquired, the better the training effect, and the target color band elimination model The better the elimination effect.

Then, based on the Retinex theory (i.e., retinal cerebral cortex theory), construct a convolutional neural network model, and use the obtained one-to-one corresponding image samples with color bands and image samples without color bands to perform color band elimination training on the convolutional neural network, Obtain the convolutional neural network model for eliminating color bands, that is, the target color band removal model.

Please refer to FIG. 2 , which is a schematic diagram of the Retinex theory provided by the embodiment of the present invention. As shown in Figure 2, the Retinex theory believes that an image can be expressed as the product of the reflection component R and the illumination component L, which can be expressed in the form of the following formula:

I = R x L

Among them, R is the reflection component, which reflects the color characteristics of the object itself, corresponding to the high-frequency part in the image, and L is the illuminance component, which reflects the brightness of the environment, and corresponds to the low-frequency part in the image.

The generation of banding is caused by the change of ambient brightness. Therefore, if the illuminance component L can be corrected and estimated from the original image S, a better R can be calculated, thereby eliminating the color band and improving the image. visual effects. In processing, the image is usually transferred to the logarithmic domain, i.e. the product relation is thus transformed into a sum relation:

log(I)=log(R)+log(L);

log(R)=log(I)-log(L).

Therefore, the core of Retinex theory is to estimate L from the original image I and remove L. Combined with the method of deep learning, a convolutional neural network model needs to be trained. The input of the convolutional neural network model is the original image I. When used, I is calculated by the convolutional neural network model network to obtain the corrected L. Through the above The formula is calculated to obtain the final result R. Considering the time cost, this process can be carried out using small images. Since the original image I retains a large amount of original image information, the restored R can still maintain a clear image quality.

Therefore, the target color band elimination model in the embodiment of the present invention adopts a convolutional neural network model based on the Retinex theory, and uses the obtained one-to-one corresponding image samples with color bands and image samples without color bands to carry out the convolutional neural network. Ribbon elimination training, the convolutional neural network model for eliminating ribbons can be obtained.

Please refer to FIG. 3 , which is a schematic diagram of a target color band elimination model provided by an embodiment of the present invention. As shown in Figure 3, the input is the original image I, F(x) represents the downsampling process, which is composed of convolutional layer and sampling layer, etc., F ^-1 (x) is the inverse process of F(x), which is the upper The sampling process is also composed of convolutional layers and sampling layers. Through the target color band elimination model, an enhanced image R is finally obtained, that is, an image after color band elimination.

(5) Step 105: output the image after removing the color band.

After the P images collected by the camera are detected by the target color band detection model, and the color band is eliminated by the color band elimination model, the image after the color band is eliminated can be output. In this way, the output image is clear, which can improve the shooting experience of the user.

In the embodiment of the present invention, the electronic device first determines the light source type according to the obtained light source type information before performing color band detection, so as to determine whether the image acquired by the camera needs to be detected and eliminated, which not only simplifies the process of color band detection, At the same time, the possibility of false detection is reduced, and the image processing speed is improved; in the process of color band detection and color band elimination, the images collected by the camera are processed by obtaining the pre-trained and learned target color band detection model and target color band elimination model Fast color band detection and color band elimination are performed, the color band detection accuracy is high, and the color band elimination effect is good, the image processing and output speed of the electronic device are significantly improved, and the user experience of the electronic device is improved.

Another embodiment of the present invention provides an image processing method, and the image processing method may include the following steps:

Step 201: Acquire consecutive P images of the target scene captured by the camera, where P is a positive integer;

Step 202: Obtain the light source category in the target scene, the light source category includes natural light source and artificial light source;

Step 203: Output an image in which the light source type is natural light source.

In this embodiment, the specific implementation process of step 201 and step 202 can be seen in the previous embodiment, and will not be repeated here. When the light source type of the target scene is a natural light source, according to the analysis of the previous embodiment, there will be no color bands in the P images. Therefore, in this case, an image whose light source type is a natural light source can be directly output. For example, if the light source category is a natural light source, output the P images. In the embodiment of the present invention, by judging whether the light source type of the target scene is a natural light source or an artificial light source, it is possible to know whether to perform color band detection on the captured image, and directly output the captured image when the light source type is a natural light source, avoiding the need for each The cumbersome steps of color band detection are performed for each captured image, which increases the image output speed and improves user experience.

Another embodiment of the present invention provides an image processing method, and the image processing method may include the following steps:

Step 301: Acquire consecutive P images of the target scene captured by the camera, where P is a positive integer;

Step 302: Identify the light source category in the target scene, the light source category includes natural light source and artificial light source;

Step 303: If the type of light source is not a natural light source, perform color band detection on the acquired P images, and determine whether a color band is detected from the P images;

Step 304: Outputting an image in which no color band is detected.

The specific implementation process of the above step 301, step 302 and step 303 can be seen in the first embodiment, and will not be repeated here. In the embodiment of the present invention, when the color band is not detected, the image in which the color band is not detected may be directly output. The embodiment of the present invention uses the target color band detection model to detect the color band of the captured image, and directly outputs the image when the color band is not detected, avoiding the cumbersome steps of eliminating the color band for each captured image, and improving The image output speed is improved, and the user experience is improved.

Please refer to FIG. 4. FIG. 4 is an electronic device provided in another embodiment of the present invention. The electronic device 400 includes:

An acquisition module 401, configured to acquire continuous P images under the target scene collected by the camera, wherein P is a positive integer;

An identification module 402, configured to identify the type of light source in the target scene, where the type of light source includes natural light source and artificial light source;

A color band detection module 403, configured to perform color band detection on the P images if the type of the light source is an artificial light source, and determine whether a color band is detected from the P images;

A color band elimination module 404, configured to perform color band elimination processing on the P images if a color band is detected from the P images;

The image output module 405 is configured to output the image after removing the color band.

Optionally, the identification module 402 includes:

A color information acquisition sub-module, configured to acquire color information by using the color sensor of the camera;

The light source information collection sub-module is configured to determine light source information according to the color information, and the light source information includes at least one of a color rendering index and a correlated color temperature;

The light source category determining submodule is configured to determine the light source category in the target scene according to the light source information.

Optionally, the image output module is further configured to output an image in which the light source type is a natural light source among the P images.

Optionally, the ribbon detection module 403 includes:

The color band detection image sample acquisition submodule is used to acquire S image samples, the S image samples include images with artificial light sources as light sources and images with natural light sources as light sources, and each image sample includes continuous M images, wherein , M=P;

The frame difference calculation sub-module is used to calculate the difference between each image in each image sample and another image, and perform image fusion on the multiple frame difference images obtained after the difference calculation to obtain the target sample image;

The color band detection model training submodule is used to establish a convolutional neural network model, and uses the target sample image to perform color band detection training on the convolutional neural network model to obtain a target color band detection model;

The detection image processing submodule is used to obtain a target detection image according to the P images;

The color band detection sub-module is used to input the target detection image into the target color band detection model to detect whether there is a color band.

Optionally, the detection image processing submodule includes:

A frame difference calculation unit, configured to calculate the difference between each of the P images and another image to obtain multiple frame difference images;

An image fusion unit, configured to perform image fusion on the plurality of frame difference images to obtain the target detection image.

Optionally, the ribbon elimination module 404 includes:

The color band elimination image sample acquisition submodule is used to acquire image samples with color bands and image samples without color bands in the same scene;

The color band elimination model training submodule is used to establish a convolutional neural network model, and uses the image samples with color bands and the image samples without color bands to perform color band elimination training on the convolutional neural network to obtain the target color band. with elimination model;

The color band elimination sub-module is configured to input the P images into the target color band elimination model, and eliminate the color bands in the P images.

In the embodiment of the present invention, the electronic device 400 first determines the light source type according to the obtained light source type information before performing color band detection, so as to determine whether the image captured by the camera needs to be detected and eliminated, which not only simplifies the process of color band detection , while reducing the possibility of false detection and improving the image processing speed; in the process of color band detection and color band elimination, the image collected by the camera is analyzed by obtaining the target color band detection model and the target color band elimination model that have been trained and learned in advance. Rapid color band detection and color band elimination are performed on the image, thereby improving the image processing and output speed of the electronic device, and improving the user experience of the electronic device.

Please refer to FIG. 5. FIG. 5 is a schematic structural diagram of an electronic device according to another embodiment of the present invention. The electronic device 50 includes but is not limited to: a radio frequency unit 51, a network module 52, an audio output unit 53, an input unit 54, a sensor 55, Display unit 56 , user input unit 57 , interface unit 58 , memory 59 , processor 510 , power supply 511 and other components. Those skilled in the art can understand that the structure of the electronic device shown in Figure 5 does not constitute a limitation on the electronic device, and the electronic device may include more or fewer components than shown in the figure, or combine some components, or different components layout. In the embodiment of the present invention, electronic devices include but are not limited to mobile phones, tablet computers, notebook computers, palmtop computers, vehicle-mounted electronic devices, wearable devices, and pedometers.

Processor 510, for:

Obtain consecutive P images of the target scene collected by the camera, where P is a positive integer;

identifying a light source category in the target scene, where the light source category includes natural light sources and artificial light sources;

If the light source category is an artificial light source, perform color band detection on the P images;

If a color band is detected from the P images, performing color band elimination processing on the P images;

Output the image with the color band removed.

In the embodiment of the present invention, before performing the color band detection, the light source category is determined according to the obtained light source category information to determine whether the image acquired by the camera needs to be detected and eliminated, which not only simplifies the process of color band detection, but also reduces the The possibility of false detection is reduced, and the image processing speed is improved.

It should be understood that, in the embodiment of the present invention, the radio frequency unit 51 can be used for sending and receiving information or receiving and sending signals during a call. Specifically, the downlink data from the base station is received and processed by the processor 510; Uplink data is sent to the base station. Generally, the radio frequency unit 51 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like. In addition, the radio frequency unit 51 can also communicate with the network and other devices through a wireless communication system.

The electronic device provides users with wireless broadband Internet access through the network module 52, such as helping users send and receive emails, browse web pages, and access streaming media.

The audio output unit 53 may convert audio data received by the radio frequency unit 51 or the network module 52 or stored in the memory 59 into an audio signal and output as sound. Also, the audio output unit 53 may also provide audio output related to a specific function performed by the electronic device 50 (eg, call signal reception sound, message reception sound, etc.). The audio output unit 53 includes a speaker, a buzzer, a receiver and the like.

The input unit 54 is used to receive audio or video signals. The input unit 54 can include a graphics processing unit (Graphics Processing Unit, GPU) 541 and a microphone 542, and the graphics processing unit 541 is to an image of a still picture or a video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode The data is processed. The processed image frames may be displayed on the display unit 56 . The image frames processed by the graphics processor 541 may be stored in the memory 59 (or other storage media) or sent via the radio frequency unit 51 or the network module 52 . The microphone 542 can receive sound and can process such sound into audio data. The processed audio data can be converted into a format that can be sent to a mobile communication base station via the radio frequency unit 51 for output in the case of a phone call mode.

The electronic device 50 also includes at least one sensor 55, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel 561 according to the brightness of the ambient light, and the proximity sensor can turn off the display panel 561 and the / or backlighting. As a kind of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes), and can detect the magnitude and direction of gravity when it is still, and can be used to identify the posture of electronic equipment (such as horizontal and vertical screen switching, related games) , magnetometer attitude calibration), vibration recognition related functions (such as pedometer, knocking), etc.; sensor 55 can also include fingerprint sensor, pressure sensor, iris sensor, molecular sensor, gyroscope, barometer, hygrometer, thermometer, Infrared sensors, etc., will not be repeated here.

The display unit 56 is used to display information input by the user or information provided to the user. The display unit 56 may include a display panel 561, and the display panel 561 may be configured in the form of a liquid crystal display (Liquid Crystal Display, LCD), an organic light-emitting diode (Organic Light-Emitting Diode, OLED), or the like.

The user input unit 57 can be used to receive input numbers or character information, and generate key signal input related to user settings and function control of the electronic device. Specifically, the user input unit 57 includes a touch panel 571 and other input devices 572 . The touch panel 571, also referred to as a touch screen, can collect touch operations of the user on or near it (for example, the user uses any suitable object or accessory such as a finger or a stylus on the touch panel 571 or near the touch panel 571). operate). The touch panel 571 may include two parts, a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, and detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and sends it to the For the processor 510, receive the command sent by the processor 510 and execute it. In addition, the touch panel 571 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. Besides the touch panel 571 , the user input unit 57 may also include other input devices 572 . Specifically, other input devices 572 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be repeated here.

Further, the touch panel 571 can be covered on the display panel 561, and when the touch panel 571 detects a touch operation on or near it, it will be sent to the processor 510 to determine the type of the touch event, and then the processor 510 can The type of event provides a corresponding visual output on the display panel 561 . Although in FIG. 5, the touch panel 571 and the display panel 561 are used as two independent components to realize the input and output functions of the electronic device, in some embodiments, the touch panel 571 and the display panel 561 can be integrated. The implementation of the input and output functions of the electronic device is not specifically limited here.

The interface unit 58 is an interface for connecting an external device to the electronic device 50 . For example, an external device may include a wired or wireless headset port, an external power (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, audio input/output (I/O) ports, video I/O ports, headphone ports, and more. Interface unit 58 may be used to receive input (eg, data information, power, etc.) from an external device and transmit the received input to one or more elements within electronic device 50 or may be used to interface transfer data between.

The memory 59 can be used to store software programs as well as various data. The memory 59 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one function required application program (such as a sound playback function, an image playback function, etc.) etc.; Data created by the use of mobile phones (such as audio data, phonebook, etc.), etc. In addition, the memory 59 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.

The processor 510 is the control center of the electronic equipment, and uses various interfaces and lines to connect various parts of the entire electronic equipment, by running or executing software programs and/or modules stored in the memory 59, and calling data stored in the memory 59 , to perform various functions of the electronic equipment and process data, so as to monitor the electronic equipment as a whole. The processor 510 may include one or more processing units; preferably, the processor 510 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem The processor mainly handles wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 510 .

The electronic device 50 can also include a power supply 511 (such as a battery) for supplying power to various components. Preferably, the power supply 511 can be logically connected to the processor 510 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. and other functions.

In addition, the electronic device 50 includes some functional modules not shown, which will not be repeated here.

Please refer to FIG. 6 . FIG. 6 is a schematic structural diagram of an electronic device according to another embodiment of the present invention. The electronic device 60 includes: a processor 61 and a memory 62 . In this embodiment of the present invention, the electronic device 60 further includes: a computer program stored in the memory 62 and operable on the processor 61. When the computer program is executed by the processor 611, it can implement each of the above-mentioned image processing method embodiments. process, and can achieve the same technical effect, in order to avoid repetition, it will not be repeated here.

An embodiment of the present invention also provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, each process of any of the above-mentioned image processing method embodiments is implemented, and can To achieve the same technical effect, in order to avoid repetition, no more details are given here. Wherein, the computer-readable storage medium is, for example, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and the like.

It should be noted that, in this document, the term "comprising", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element.

Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation. Based on such an understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products are stored in a storage medium (such as ROM/RAM, disk, CD) contains a plurality of instructions to make an electronic device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in various embodiments of the present invention.

Embodiments of the present invention have been described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementations, and the above-mentioned specific implementations are only illustrative, rather than restrictive, and those of ordinary skill in the art will Under the enlightenment of the present invention, without departing from the gist of the present invention and the protection scope of the claims, many forms can also be made, all of which belong to the protection of the present invention.

Claims (12)

1. A kind of image processing method, is applied to electronic equipment, is characterized in that, described method comprises: Obtain consecutive P images of the target scene collected by the camera, where P is a positive integer; identifying a light source category in the target scene, where the light source category includes natural light sources and artificial light sources; If the light source category is an artificial light source, perform color band detection on the P images; If a color band is detected from the P images, performing color band elimination processing on the P images; Output the image after removing the color band; If the type of the light source is an artificial light source, the step of performing color band detection on the P images includes: Obtain a target detection image according to the P images; The target detection image is input into the target color band detection model to detect whether there is a color band; Before the target detection image is input to the target ribbon detection model, it also includes: Acquire S image samples, the S image samples include images using artificial light sources as light sources and images using natural light sources as light sources, each image sample includes consecutive M images, and each interval of the target from the acquired P images The duration is selected from the M consecutive images, where P and M are both positive integers, and M≤P; performing difference calculation between each image in each image sample and another image, and performing image fusion on multiple frame difference images obtained after the difference calculation to obtain a target sample image; A convolutional neural network model is established, and the color band detection training is performed on the convolutional neural network model by using the target sample image to obtain the target color band detection model. 2. The image processing method according to claim 1, wherein the step of identifying the category of the light source under the target scene comprises: Obtain color information by using the color sensor of the camera; Determine light source information according to the color information, where the light source information includes at least one of a color rendering index and a correlated color temperature; According to the light source information, determine a light source category in the target scene. 3. The image processing method according to claim 1, characterized in that, after identifying the light source category under the target scene, the method further comprises: If the light source category is a natural light source, output the P images. 4. The image processing method according to claim 1, wherein the step of obtaining the target detection image according to the P images comprises: Perform difference calculation between each of the P images and another image to obtain multiple frame difference images; Image fusion is performed on the multiple frame difference images to obtain a target detection image. 5. The image processing method according to claim 1, wherein if a color band is detected from the P images, the step of performing color band elimination processing on the P images comprises: Input the P images into the target color band elimination model, and eliminate the color bands in the P images; Before the P images are input to the target color band elimination model, it also includes: Obtain image samples with color bands and image samples without color bands in the same scene; Establish a convolutional neural network model based on retinal cerebral cortex theory, use the image samples with color bands and the image samples without color bands to perform color band elimination training on the convolutional neural network, and obtain the target color band elimination Model. 6. An electronic device, characterized in that it comprises: The obtaining module is used to obtain continuous P images under the target scene collected by the camera, wherein P is a positive integer; An identification module, configured to identify the category of light sources in the target scene, where the categories of light sources include natural light sources and artificial light sources; A color band detection module, configured to perform color band detection on the P images if the light source type is an artificial light source; A color band elimination module, configured to perform color band elimination processing on the P images if a color band is detected from the P images; Image output module, for outputting the image after removing the color band; The ribbon detection module includes: The color band detection image sample acquisition submodule is used to acquire S image samples, the S image samples include images with artificial light sources as light sources and images with natural light sources as light sources, and each image sample includes continuous M images, from Selecting the M continuous images for each target time interval among the acquired P images, where P and M are both positive integers, and M≤P; The frame difference calculation sub-module is used to calculate the difference between each image in each image sample and another image, and perform image fusion on the multiple frame difference images obtained after the difference calculation to obtain the target sample image; The color band detection model training submodule is used to establish a convolutional neural network model, and uses the target sample image to perform color band detection training on the convolutional neural network model to obtain a target color band detection model; The detection image processing submodule is used to obtain a target detection image according to the P images; The color band detection sub-module is used to input the target detection image into the target color band detection model to detect whether there is a color band. 7. The electronic device according to claim 6, wherein the identification module comprises: A color information acquisition sub-module, configured to acquire color information by using the color sensor of the camera; The light source information collection sub-module is configured to determine light source information according to the color information, and the light source information includes at least one of a color rendering index and a correlated color temperature; The light source category determining submodule is configured to determine the light source category in the target scene according to the light source information. 8 . The electronic device according to claim 6 , wherein the image output module is further configured to output an image in which the light source type is a natural light source among the P images. 9. The electronic device according to claim 6, wherein the detection image processing submodule comprises: A frame difference calculation unit, configured to calculate the difference between each of the P images and another image to obtain multiple frame difference images; An image fusion unit, configured to perform image fusion on the plurality of frame difference images to obtain the target detection image. 10. The electronic device according to claim 6, wherein the color band elimination module comprises: The color band elimination image sample acquisition submodule is used to acquire image samples with color bands and image samples without color bands in the same scene; The color band elimination model training submodule is used to establish a convolutional neural network model based on the retinal cerebral cortex theory, and uses the image samples with color bands and the image samples without color bands to perform color banding on the convolutional neural network Eliminate the training to get the target ribbon elimination model; The color band elimination sub-module is configured to input the P images into the target color band elimination model, and eliminate the color bands in the P images. 11. An electronic device, characterized by comprising a processor, a memory, and a computer program stored on the memory and operable on the processor, when the computer program is executed by the processor, the The steps of the image processing method described in any one of 1 to 5 are required. 12. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the image according to any one of claims 1 to 5 is realized The steps of the processing method.

Images